3 papers
cs.CV2026
STENet: Superpixel Token Enhancing Network for RGB-D Salient Object Detection
Jianlin Chen, Gongyang Li, Zhijiang Zhang +2
Transformer-based methods for RGB-D Salient Object Detection (SOD) have gained significant interest, owing to the transformer's exceptional capacity to capture long-range pixel dep…
cs.CV2024
DefFiller: Mask-Conditioned Diffusion for Salient Steel Surface Defect Generation
Yichun Tai, Zhenzhen Huang, Tao Peng +1
Current saliency-based defect detection methods show promise in industrial settings, but the unpredictability of defects in steel production environments complicates dataset creati…
cs.CV2024
Defect Image Sample Generation With Diffusion Prior for Steel Surface Defect Recognition
Yichun Tai, Kun Yang, Tao Peng +2
The task of steel surface defect recognition is an industrial problem with great industry values. The data insufficiency is the major challenge in training a robust defect recognit…